OpenAI trained GPT-Red, an internal-only attacker model, using self-play reinforcement learning against a population of defender LLMs. It beat human red-teamers 84% to 13% on a replicated indirect ...
This is a Triton implementation of the Flash Attention v2 algorithm from Tri Dao (https://tridao.me/publications/flash2/flash2.pdf) ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results